Noometry

Model comparison

Dolly 2.0-12b vs Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 24.9 on the Noometry Index.

Last verified . 10 shared benchmarks.

Dolly 2.0-12b Databricks

24.9

Rank #339 Confirmed

Gemini 2.5 Flash-Lite Google

36.4

Rank #208 Confirmed

Summary

  • They share 10 benchmarks with published results for both. Dolly 2.0-12b scores higher in 0 categories and Gemini 2.5 Flash-Lite in 6 categories; 6 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Gemini 2.5 Flash-Lite leads 57.0 to 15.3.
  • Dolly 2.0-12b has downloadable open weights; the other is API-only.

Side by side

Dolly 2.0-12bGemini 2.5 Flash-Lite
ProviderDatabricksGoogle
Noometry Index24.936.4
Released2023-04-112025-06-17
WeightsOpenProprietary
Context window—1.05M
Max output—66K
Input $ / M tokens—$0.10
Output $ / M tokens—$0.40
Results tracked1733

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Gemini 2.5 Flash-Lite leads

Dolly 2.0-12b: 23.0 (#327), Gemini 2.5 Flash-Lite: 38.0 (#167)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
LMArena Coding7761373
WeirdML—35.2%
ALE-Bench—325.9

Agentic & Tool Use Not comparable

Dolly 2.0-12b: —, Gemini 2.5 Flash-Lite: 27.8 (#89)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
Berkeley Function Calling Leaderboard—36.9%

Reasoning Gemini 2.5 Flash-Lite leads

Dolly 2.0-12b: 14.6 (#315), Gemini 2.5 Flash-Lite: 21.5 (#196)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
LMArena Hard Prompts8041377
Epoch Capabilities Index88.94133.93
Kagi LLM Benchmark—40.5%
DTBench—62.8%
LMCA—18.1%
HellaSwag70.8%—
PIQA75.4%—
WinoGrande61.8%—

Math Gemini 2.5 Flash-Lite leads

Dolly 2.0-12b: 25.0 (#250), Gemini 2.5 Flash-Lite: 35.5 (#144)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
LMArena Math8711373
Omni-MATH—48%

Knowledge Not comparable

Dolly 2.0-12b: —, Gemini 2.5 Flash-Lite: 32.1 (#206)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
MMLU-Pro—53.7%
Vectara Hallucination Rate—3.3%
GPQA (HELM)—30.9%
LMArena Expert—1373
ARC (AI2) Challenge39.6%—
BoolQ56.3%—
MMLU26.2%—
OpenBookQA39.2%—

Multimodal Not comparable

Dolly 2.0-12b: —, Gemini 2.5 Flash-Lite: 28.6 (#109)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
LMArena Vision—1198
VPCT—30%

Multilingual Gemini 2.5 Flash-Lite leads

Dolly 2.0-12b: 17.4 (#291), Gemini 2.5 Flash-Lite: 49.5 (#129)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
LMArena Non-English8361369
LMArena Chinese8361404
LMArena French—1388
LMArena German—1390
LMArena Japanese—1359
LMArena Korean—1358
LMArena Russian—1373
LMArena Spanish—1396

Instruction Following Gemini 2.5 Flash-Lite leads

Dolly 2.0-12b: 38.9 (#299), Gemini 2.5 Flash-Lite: 70.2 (#163)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
LMArena Instruction Following8141366
IFEval—81%

Long Context Not comparable

Dolly 2.0-12b: —, Gemini 2.5 Flash-Lite: 33.3 (#257)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
Fiction.LiveBench—47.2%
LMArena Longer Query—1373

Writing & Preference Gemini 2.5 Flash-Lite leads

Dolly 2.0-12b: 15.3 (#306), Gemini 2.5 Flash-Lite: 57.0 (#130)

BenchmarkDolly 2.0-12bGemini 2.5 Flash-Lite
LMArena Text8511379
LMArena Creative Writing8641366
LMArena Multi-Turn7401367
WildBench—81.8%

Frequently asked questions

Is Dolly 2.0-12b better than Gemini 2.5 Flash-Lite?

Gemini 2.5 Flash-Lite is the stronger model overall, scoring 36.4 to 24.9 on the Noometry Index.

Is Dolly 2.0-12b or Gemini 2.5 Flash-Lite better for coding?

Gemini 2.5 Flash-Lite scores higher on coding benchmarks: 38.0 versus 23.0 in the Noometry coding category.

How many benchmarks do Dolly 2.0-12b and Gemini 2.5 Flash-Lite share?

10 benchmarks have published results for both models. Dolly 2.0-12b has 17 scored results on Noometry and Gemini 2.5 Flash-Lite has 33.

Related comparisons

Go deeper